Classification of Computed Tomography Images in Different Slice Positions Using Deep Learning

Table 5

Recall, precision, F-measure, and overall accuracy for each dataset in AlexNet and GoogLeNet.

	CNN architecture	Dataset
		0.1K	0.5K	1K	2K	3K	4K	5K	6K	7K	8K	9K	10K
Recall	AlexNet	0.20	0.39	0.52	0.53	0.61	0.67	0.61	0.67	0.67	0.65	0.64	0.62
	GoogLeNet	0.15	0.38	0.57	0.62	0.65	0.68	0.61	0.65	0.69	0.62	0.67	0.69
Precision	AlexNet	0.20	0.39	0.53	0.54	0.61	0.67	0.65	0.69	0.70	0.68	0.67	0.64
	GoogLeNet	0.15	0.41	0.58	0.62	0.65	0.68	0.63	0.66	0.71	0.64	0.70	0.70
F-measure	AlexNet	0.14	0.35	0.49	0.50	0.60	0.65	0.59	0.65	0.66	0.63	0.62	0.59
	GoogLeNet	0.11	0.35	0.54	0.61	0.64	0.67	0.59	0.63	0.67	0.60	0.65	0.68
Overall accuracy	AlexNet	0.20	0.39	0.52	0.53	0.61	0.66	0.61	0.67	0.67	0.65	0.63	0.62
	GoogLeNet	0.15	0.38	0.57	0.62	0.65	0.68	0.61	0.65	0.69	0.62	0.67	0.69